{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler", "description": "A powerful web crawler that extracts text content from websites, optimized for AI models, Large Language Models (LLMs), vector databases, and Retrieval-Augmented Generation (RAG) pipelines.", "version": "0.0", "x-build-id": "Uy0RAOT2ez9Zv4tkS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jasondev~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jasondev-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jasondev~website-content-crawler/runs": { "post": { "operationId": "runs-sync-jasondev-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jasondev~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-jasondev-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more URLs of the pages where the crawler will start. The crawler will additionally only crawl sub-pages of these URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlerType": { "title": "Crawler type", "enum": [ "playwright:chrome", "playwright:firefox", "cheerio", "jsdom" ], "type": "string", "description": "Select the crawling engine. Playwright browsers can handle JavaScript-heavy sites but are slower. Cheerio is a fast HTTP client but cannot execute JavaScript.", "default": "cheerio" }, "maxCrawlDepth": { "title": "Max crawling depth", "minimum": 0, "type": "integer", "description": "The maximum number of links starting from the start URL that the crawler will recursively descend. Start URLs have a depth of 0, pages linked from start URLs have a depth of 1, etc. By setting this to 0, the crawler will only crawl start URLs.", "default": 1 }, "maxCrawlPages": { "title": "Max pages", "minimum": 0, "type": "integer", "description": "The maximum number of pages to crawl. The crawler will stop after reaching this number. This includes the start URLs.", "default": 100 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 0, "type": "integer", "description": "Maximum number of pages to crawl per minute. Set to 0 for unlimited.", "default": 0 }, "readableTextCharThreshold": { "title": "Readable text char threshold", "minimum": 0, "type": "integer", "description": "Minimum number of readable characters required for a page to be included in results. Pages with less text will be skipped.", "default": 100 }, "removeCookieWarnings": { "title": "Remove cookie warnings", "type": "boolean", "description": "Remove common cookie consent dialogs and banners from pages before extracting content.", "default": true }, "clickElementsCssSelector": { "title": "Click elements CSS selector", "type": "string", "description": "CSS selector for elements to click on each page (e.g., to expand content). The crawler will click all matching elements before extracting content." }, "htmlTransformer": { "title": "HTML transformer", "enum": [ "readableText", "none" ], "type": "string", "description": "How to transform HTML before text extraction.", "default": "readableText" }, "removeElementsCssSelector": { "title": "Remove elements CSS selector", "type": "string", "description": "CSS selector for elements to remove from pages before extracting content (e.g., 'nav, footer, .ads')." }, "keepElementsCssSelector": { "title": "Keep elements CSS selector", "type": "string", "description": "CSS selector for elements to keep. All other elements will be removed. Takes precedence over 'Remove elements CSS selector'." }, "renderingTypeDetectionPercentage": { "title": "Rendering type detection percentage", "minimum": 0, "maximum": 100, "type": "integer", "description": "Percentage of pages to automatically check if they need JavaScript rendering. If most pages work without JS, the crawler will switch to faster HTTP mode.", "default": 10 }, "saveHtml": { "title": "Save HTML", "type": "boolean", "description": "Save the raw HTML of each page to the key-value store.", "default": false }, "saveMarkdown": { "title": "Save Markdown", "type": "boolean", "description": "Convert HTML to Markdown and save it in the output.", "default": true }, "saveFiles": { "title": "Save files", "type": "boolean", "description": "Download and save linked files (PDFs, documents, etc.) from crawled pages.", "default": false }, "saveScreenshots": { "title": "Save screenshots", "type": "boolean", "description": "Save screenshots of each page (only available with Playwright crawlers).", "default": false }, "maxScrollHeightPixels": { "title": "Max scroll height (pixels)", "minimum": 0, "type": "integer", "description": "Maximum height to scroll on pages with infinite scroll. Set to 0 to disable scrolling.", "default": 0 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings for the crawler." }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Maximum number of times to retry failed requests.", "default": 3 }, "debugMode": { "title": "Debug mode", "type": "boolean", "description": "Enable detailed debug logging.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }